Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3400 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.4352. Min Act: -0.0000

Data Index: 500121 (The Pile)

Max Activating Token Index: 802

Text #1

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3210. Min Act: -0.0000

Data Index: 730217 (The Pile)

Max Activating Token Index: 492

Text #2

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3404. Min Act: -0.0000

Data Index: 1152766 (The Pile)

Max Activating Token Index: 91

Text #3

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3504. Min Act: -0.0000

Data Index: 1390389 (The Pile)

Max Activating Token Index: 347

Text #4

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3246. Min Act: -0.0000

Data Index: 434655 (The Pile)

Max Activating Token Index: 825

Text #5

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1069084 (The Pile)

Max Activating Token Index: 623

Text #6

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3173. Min Act: -0.0000

Data Index: 677839 (The Pile)

Max Activating Token Index: 928

Text #7

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1422699 (The Pile)

Max Activating Token Index: 729

Text #8

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3385. Min Act: -0.0000

Data Index: 1143559 (The Pile)

Max Activating Token Index: 936

Text #9

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3375. Min Act: -0.0000

Data Index: 69364 (The Pile)

Max Activating Token Index: 379

Text #10

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3242. Min Act: -0.0000

Data Index: 1280272 (The Pile)

Max Activating Token Index: 410

Text #11

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3110. Min Act: -0.0000

Data Index: 1660866 (The Pile)

Max Activating Token Index: 926

Text #12

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3285. Min Act: -0.0000

Data Index: 500889 (The Pile)

Max Activating Token Index: 997

Text #13

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3094. Min Act: -0.0000

Data Index: 1454569 (The Pile)

Max Activating Token Index: 989

Text #14

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1316561 (The Pile)

Max Activating Token Index: 702

Text #15

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1403513 (The Pile)

Max Activating Token Index: 817

Text #16

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3182. Min Act: -0.0000

Data Index: 1608703 (The Pile)

Max Activating Token Index: 999

Text #17

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3293. Min Act: -0.0000

Data Index: 1090662 (The Pile)

Max Activating Token Index: 420

Text #18

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3154. Min Act: -0.0000

Data Index: 583264 (The Pile)

Max Activating Token Index: 810

Text #19

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3056. Min Act: -0.0000

Data Index: 1213735 (The Pile)

Max Activating Token Index: 859